CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

to-issues

Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.

89

1.11x
Quality

92%

Does it follow best practices?

Impact

78%

1.11x

Average score across 3 eval scenarios

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

92%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, well-sequenced instruction-only skill: lean prose, a concrete template, and a user-approval checkpoint that validates the batch publishing step before it runs. The single notable gap is the absence of a worked example showing what a good slice breakdown looks like.

Suggestions

Add a short worked example (3-4 slice titles with HITL/AFK and blocked-by fields) so the desired granularity is concrete rather than only described.

Name or link the triage label(s) to use when publishing "ready" issues, since the label vocabulary currently depends entirely on /setup-matt-pocock-skills having been run.

DimensionReasoningScore

Conciseness

The ~75-line body is a lean numbered process with a delimited rules block and a reusable template; it never explains concepts Claude already knows (what an issue tracker or PRD is). Only trivial duplication exists (the intro sentence restates the description), so it sits at anchor 5 rather than 4.

5 / 5

Actionability

Concrete, executable guidance throughout: exact quiz questions, a copy-paste issue-template, HITL/AFK typing, dependency-order publishing, and a safety constraint ("Do NOT close or modify any parent issue"). Not 5 because there is no worked example of a sliced breakdown and the triage label vocabulary is deferred to /setup-matt-pocock-skills, leaving minor gaps; instruction-only format itself is not penalized per the rubric's scoring notes.

4 / 5

Workflow Clarity

A clear five-step sequence with an explicit validation checkpoint ("Iterate until the user approves the breakdown") gating the batch publish, plus dependency-ordered publishing so blocker references are real. The feedback loop exists, so the batch-operation cap at 3 does not apply; this matches anchor 5 (explicit validation, feedback loop, checklist of quiz questions).

5 / 5

Progressive Disclosure

The skill is a self-contained single file with no bundle directories; sections plus the <vertical-slice-rules> and <issue-template> blocks make navigation trivial, and nothing here would benefit from splitting into reference files. Well-organized sections with no external references needed match the top anchor for a self-contained skill.

5 / 5

Total

19

/

20

Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: explicit what-and-when structure, natural trigger phrasings, and distinctive niche vocabulary in third-person voice. The only gap is that it expresses one core action, so breadth of listed capabilities is slightly below the top specificity anchor.

DimensionReasoningScore

Specificity

"Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices" names the action, artifact, venue, and method, matching anchor 4 (specific actions with minor gaps). Not 5 because it captures a single decomposition/publish action rather than multiple distinct actions; not 3 because the one action is specified far more concretely than 1-2 generic actions. Third person voice, so no voice penalty applies.

4 / 5

Completeness

It explicitly answers both what (break plans/specs/PRDs into independently-grabbable tracer-bullet issues on the tracker) and when ("Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues") with concrete trigger phrases, exactly matching the anchor-5 example pattern.

5 / 5

Trigger Term Quality

The when-clause offers natural user phrasings ("convert a plan into issues", "create implementation tickets", "break down work into issues") with good coverage of the trigger space. Not 5 because common variations such as "task breakdown", "split the PRD", or "create tickets from stories" are missing; clearly above anchor 3's partial coverage.

4 / 5

Distinctiveness Conflict Risk

"independently-grabbable issues" and "tracer-bullet vertical slices" carve out a clear niche with trigger phrases unlikely to fire for unrelated skills. Overlap risk with generic issue-management or planning skills is minimal, matching anchor 5.

5 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

whimzyLive/nightshift-ai

Path

plugins/sdlc/skills/to-issues/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.